Wei Li

Orcid: 0000-0002-1221-7915

Affiliations:
  • Microsoft
  • NewsBreak, Seattle, WA, USA (former)
  • Google Research, Zurich, Switzerland (former)
  • Chinese University of Hong Kong, Hong Kong (former)


According to our database1, Wei Li authored at least 13 papers between 2010 and 2023.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2023
Learning to Overcome Noise in Weak Caption Supervision for Object Detection.
IEEE Trans. Pattern Anal. Mach. Intell., April, 2023

2019
Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

2018
Learning to discover and localize visual objects with open vocabulary.
CoRR, 2018

Appearance-and-Relation Networks for Video Classification.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

2017
WebVision Database: Visual Learning and Understanding from Web Data.
CoRR, 2017

WebVision Challenge: Visual Learning and Understanding With Web Data.
CoRR, 2017

2014
Scene-Specific Pedestrian Detection for Static Video Surveillance.
IEEE Trans. Pattern Anal. Mach. Intell., 2014

DeepReID: Deep Filter Pairing Neural Network for Person Re-identification.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

2013
Dimensionality Reduction with Generalized Linear Models.
Proceedings of the IJCAI 2013, 2013

Locally Aligned Feature Transforms across Views.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012
Transferring a generic pedestrian detector towards specific scenes.
Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

Human Reidentification with Transferred Metric Learning.
Proceedings of the Computer Vision - ACCV 2012, 2012

2010
Term Filtering with Bounded Error.
Proceedings of the ICDM 2010, 2010


  Loading...